神经机器翻译高效解码算法的探索
Exploring Recombination for Efficient Decoding of Neural Machine Translation
摘要：
在神经机器翻译（NMT）中，解码器可以通过神经连接和表示来捕获整个预测历史的特征。这意味着带有不同前缀的部分假设将被不同地看待，无论它们多么相似。然而，这可能是低效的，因为某些部分假设可能仅包含不会影响未来预测的局部差异。在这项工作中，我们介绍了重组NMT解码的基础上的概念的“等价”的部分假设。启发式地，我们使用一个简单的基于$n$ -gram后缀的等价函数，并将其适配到束搜索解码中。通过对大规模汉英和英德翻译任务的实验，我们证明了该方法能够以较小的波束尺寸获得相似的翻译质量，使得NMT解码效率更高。
英文摘要：
In Neural Machine Translation (NMT), the decoder can capture the features of the entire prediction history with neural connections and representations. This means that partial hypotheses with different prefixes will be regarded differently no matter how similar they are. However, this might be inefficient since some partial hypotheses can contain only local differences that will not influence future predictions. In this work, we introduce recombination in NMT decoding based on the concept of the "equivalence" of partial hypotheses. Heuristically, we use a simple $n$-gram suffix based equivalence function and adapt it into beam search decoding. Through experiments on large-scale Chinese-to-English and English-to-Germen translation tasks, we show that the proposed method can obtain similar translation quality with a smaller beam size, making NMT decoding more efficient.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
